© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 5246
    Prev
    Next
    INDEX
    Explanations

    instances where the text is referring to looking at something in a figurative or literal sense

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "look at" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glass
    -0.73
    marine
    -0.72
    vous
    -0.71
    NL
    -0.68
    thumbnails
    -0.68
    quartered
    -0.66
    mouth
    -0.63
    pite
    -0.63
    ogn
    -0.63
    reditary
    -0.62
    POSITIVE LOGITS
    ebin
    0.90
     least
    0.84
    ertodd
    0.79
    aeper
    0.76
    DragonMagazine
    0.75
    ãĤ´ãĥ³
    0.72
    abase
    0.72
    rical
    0.70
     ours
    0.69
     liberty
    0.68
    Activations Density 0.054%

    No Known Activations